English
Related papers

Related papers: MagR: Weight Magnitude Reduction for Enhancing Pos…

200 papers

Large Vision Language Models (LVLMs) have achieved remarkable success in a range of downstream tasks that require multimodal interaction, but their capabilities come with substantial computational and memory overhead, which hinders…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Ziwei Xiang , Fanhu Zeng , Hongjian Fang , Rui-Qi Wang , Renxing Chen , Yanan Zhu , Yi Chen , Peipei Yang , Xu-Yao Zhang

Existing post-training quantization methods for large language models (LLMs) offer remarkable success. However, the increasingly marginal performance gains suggest that existing quantization strategies are insufficient to support the…

Machine Learning · Computer Science 2025-10-28 Jiaqi Zhao , Miao Zhang , Deng Xiang , Ming Li , Weili Guan , Liqiang Nie

Quantization is an effective strategy to reduce the storage and computation footprint of large language models (LLMs). Post-training quantization (PTQ) is a leading approach for compressing LLMs. Popular weight quantization procedures,…

Machine Learning · Computer Science 2026-05-13 Ryan Lucas , Mehdi Makni , Xiang Meng , Adam Deng , Rahul Mazumder

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

Machine Learning · Computer Science 2024-09-04 Yelysei Bondarenko , Riccardo Del Chiaro , Markus Nagel

Fine-tuning pre-trained diffusion models under limited budgets has gained great success. In particular, the recent advances that directly fine-tune the quantized weights using Low-rank Adaptation (LoRA) further reduces training costs.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Hang Guo , Yawei Li , Tao Dai , Shu-Tao Xia , Luca Benini

We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We leverage weight normalization as a means of constraining parameters during…

Machine Learning · Computer Science 2023-02-01 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig

While post-training compression techniques effectively reduce the memory footprint, latency, and power consumption of Large Language Models (LLMs), they often result in noticeable accuracy degradation and remain limited by hardware and…

Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization level scheme. However, this often introduces large errors due to…

Machine Learning · Computer Science 2025-11-26 Ziteng Sun , Adrian Benton , Samuel Kushnir , Asher Trockman , Vikas Singh , Suhas Diggavi , Ananda Theertha Suresh

Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primary deployment concern. Weight quantization is the standard tool for acceleration, but…

Machine Learning · Computer Science 2026-05-12 Euntae Choi , Sumin Song , Sungjoo Yoo

The growing number of parameters and computational demands of large language models (LLMs) present significant challenges for their efficient deployment. Recently, there is an increasing interest in quantizing weights to extremely low…

Machine Learning · Computer Science 2025-02-18 Cheng Zhang , Jeffrey T. H. Wong , Can Xiao , George A. Constantinides , Yiren Zhao

Recently, Sharma et al. suggested a method called Layer-SElective-Rank reduction (LASER) which demonstrated that pruning high-order components of carefully chosen LLM's weight matrices can boost downstream accuracy -- without any…

Machine Learning · Computer Science 2025-10-24 Shiva Sreeram , Alaa Maalouf , Pratyusha Sharma , Daniela Rus

Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retraining. However, existing methods either (1) fail to account…

Machine Learning · Computer Science 2025-09-23 Jinuk Kim , Marwa El Halabi , Wonpyo Park , Clemens JS Schaefer , Deokjae Lee , Yeonhong Park , Jae W. Lee , Hyun Oh Song

Various post-training uniform quantization methods have usually been studied based on convex optimization. As a result, most previous ones rely on the quantization error minimization and/or quadratic approximations. Such approaches are…

Machine Learning · Computer Science 2021-05-06 Byeongwook Kim , Dongsoo Lee , Yeonju Ro , Yongkweon Jeon , Se Jung Kwon , Baeseong Park , Daehwan Oh

As Large Language Models (LLMs) are frequently updated, LoRA weights trained on earlier versions quickly become obsolete. The conventional practice of retraining LoRA weights from scratch on the latest model is costly, time-consuming, and…

Machine Learning · Computer Science 2025-05-21 Yanan Li , Fanxu Meng , Muhan Zhang , Shiai Zhu , Shangguang Wang , Mengwei Xu

Regularization is a set of techniques that are used to improve the generalization ability of deep neural networks. In this paper, we introduce weight compander (WC), a novel effective method to improve generalization by reparameterizing…

Machine Learning · Computer Science 2023-06-30 Rinor Cakaj , Jens Mehnert , Bin Yang

We introduce ReALLM, a novel approach for compression and memory-efficient adaptation of pre-trained language models that encompasses most of the post-training quantization and fine-tuning methods for a budget of <4 bits. Pre-trained…

Machine Learning · Computer Science 2024-05-24 Louis Leconte , Lisa Bedin , Van Minh Nguyen , Eric Moulines

Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and…

Machine Learning · Statistics 2026-04-22 Ba-Hien Tran , Van Minh Nguyen

Post-training quantization (PTQ) compresses the weights and activations of large language models (LLMs) into low-precision representations to reduce memory footprint and accelerate inference. However, the presence of outliers in weights and…

Computation and Language · Computer Science 2026-02-17 Yesheng Liang , Haisheng Chen , Zihan Zhang , Song Han , Zhijian Liu

Post-training quantization (PTQ) is a neural network compression technique that converts a full-precision model into a quantized model using lower-precision data types. Although it can help reduce the size and computational cost of deep…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Jiawei Liu , Lin Niu , Zhihang Yuan , Dawei Yang , Xinggang Wang , Wenyu Liu

Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Cuong Pham , Hoang Anh Dung , Cuong C. Nguyen , Trung Le , Dinh Phung , Gustavo Carneiro , Thanh-Toan Do